Kimi K3 on Fireworks: Frontier Intelligence You Can Own

Model Library/Deepseek/DeepSeek R1 Distill Qwen 7B
Deepseek Logo Mark

DeepSeek R1 Distill Qwen 7B

Ready
Deploy on Demand
model path:accounts/fireworks/models/deepseek-r1-distill-qwen-7b

Qwen 7B distilled with reasoning from Deepseek R1

DeepSeek R1 Distill Qwen 7B API Features

On-demand Deployment

Docs

On-demand deployments allow you to use DeepSeek R1 Distill Qwen 7B on dedicated GPUs with Fireworks' high-performance serving stack with high reliability and no rate limits.

Metadata

State
Ready
Created on
1/22/2025
Kind
Base model
Provider
Deepseek
Hugging Face
deepseek-ai/DeepSeek-R1-Distill-Qwen-7B

Specification

Calibrated
Yes
Mixture-of-Experts
No
Parameters
7.61B

Supported Functionality

Fine-tuning
Not supported
Serverless
Not supported
Context Length
131k tokens
Function Calling
Not supported
Embeddings
Not supported
Rerankers
Not supported
Support image input
Not supported